The authors first tested the assumption behind training-free safety measures: that unsafe content can be modeled as a single global subspace in the text encoder.
Local counterfactual edits outperform global unsafe subspace removal
Training-free safeguard CALM selectively suppresses unsafe image generations by routing prompts to category-specific safe directions.
Big Tech
NaHyeon Park · Minhyun Lee · Hyunjung Shim
KAIST · Samsung Electronics
Research Digest··2 min read
Park, Lee, and Shim analyze why global safety signals fail in text-to-image models and propose CALM, which uses prompt-local counterfactual pairs to edit token representations.
Why this paper
From Samsung Electronics and KAIST
In one line
Text-to-image safety fails when using a single global unsafe subspace due to a coverage-selectivity trade-off.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ✓Limitations stated by the authors
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§